© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 258
    Prev
    Next
    INDEX
    Explanations

    numbers and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _),
    -0.99
    +)$
    -0.96
    ctober
    -0.95
    𔘓
    -0.94
     rhythmic
    -0.92
    Ű
    -0.92
    élimin
    -0.91
    贋
    -0.90
    Sze
    -0.89
    瓩
    -0.89
    POSITIVE LOGITS
     these
    1.04
     instead
    0.96
    A
    0.86
     umane
    0.86
     interessanti
    0.85
    ISTRO
    0.85
    E
    0.84
    0
    0.84
     comuni
    0.84
     into
    0.84
    Activations Density 0.012%

    No Known Activations